PLearn::MulticlassLossVariable Class Reference

cost = sum_i {cost_i}, with cost_i = 1 if (target_i == 1 && output_i < 1/2) cost_i = 1 if (target_i == 0 && output_i > 1/2) cost_i = 0 otherwise More...

#include <MulticlassLossVariable.h>

Inheritance diagram for PLearn::MulticlassLossVariable:

[legend]Collaboration diagram for PLearn::MulticlassLossVariable:

[legend]List of all members.

Public Member Functions
	MulticlassLossVariable ()
	Default constructor for persistence.
	MulticlassLossVariable (Variable *netout, Variable *target)
	PLEARN_DECLARE_OBJECT (MulticlassLossVariable)
virtual void	build ()
	Should call simply inherited::build(), then this class's build_().
virtual void	recomputeSize (int &l, int &w) const
	Recomputes the length l and width w that this variable should have, according to its parent variables.
virtual void	fprop ()
	compute output given input
virtual void	bprop ()
	can't bprop through a hard classification error...
Protected Member Functions
void	build_ ()
Private Types
typedef BinaryVariable	inherited

---

Detailed Description

cost = sum_i {cost_i}, with cost_i = 1 if (target_i == 1 && output_i < 1/2) cost_i = 1 if (target_i == 0 && output_i > 1/2) cost_i = 0 otherwise

Definition at line 57 of file MulticlassLossVariable.h.

---

Member Typedef Documentation

typedef BinaryVariable PLearn::MulticlassLossVariable::inherited [private]

Reimplemented from PLearn::BinaryVariable. Definition at line 59 of file MulticlassLossVariable.h. Referenced by MulticlassLossVariable().

---

Constructor & Destructor Documentation

PLearn::MulticlassLossVariable::MulticlassLossVariable (   )  [inline]

Default constructor for persistence. Definition at line 63 of file MulticlassLossVariable.h.

PLearn::MulticlassLossVariable::MulticlassLossVariable (  Variable *  netout, Variable *  target )

Definition at line 55 of file MulticlassLossVariable.cc. References build_(), and inherited.

---

Member Function Documentation

virtual void PLearn::MulticlassLossVariable::bprop (   )  [inline, virtual]

can't bprop through a hard classification error... Implements PLearn::Variable. Definition at line 73 of file MulticlassLossVariable.h.

void PLearn::MulticlassLossVariable::build (   )  [virtual]

Should call simply inherited::build(), then this class's build_(). This method should be callable again at later times, after modifying some option fields to change the "architecture" of the object. Reimplemented from PLearn::Variable. Definition at line 62 of file MulticlassLossVariable.cc. References build_().

void PLearn::MulticlassLossVariable::build_ (   )  [protected]

This method should be redefined in subclasses and do the actual building of the object according to previously set option fields. Constructors can just set option fields, and then call build_. This method is NOT virtual, and will typically be called only from three places: a constructor, the public virtual build() method, and possibly the public virtual read method (which calls its parent's read). build_() can assume that it's parent's build_ has already been called. Reimplemented from PLearn::Variable. Definition at line 69 of file MulticlassLossVariable.cc. References PLERROR. Referenced by build(), and MulticlassLossVariable().

void PLearn::MulticlassLossVariable::fprop (   )  [virtual]

compute output given input Implements PLearn::Variable. Definition at line 83 of file MulticlassLossVariable.cc.

PLearn::MulticlassLossVariable::PLEARN_DECLARE_OBJECT (  MulticlassLossVariable   )

void PLearn::MulticlassLossVariable::recomputeSize (  int &  l, int &  w )  const [virtual]

Recomputes the length l and width w that this variable should have, according to its parent variables. This is used for ex. by sizeprop() The default version stupidly returns the current dimensions, so make sure to overload it in subclasses if this is not appropriate. Reimplemented from PLearn::Variable. Definition at line 79 of file MulticlassLossVariable.cc.

---

The documentation for this class was generated from the following files:

• MulticlassLossVariable.h
• MulticlassLossVariable.cc

---